Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash

    The neuron never activates—it appears to be a non-functional or “dead” neuron.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     extrad
    -0.07
     міль
    -0.07
     المؤ
    -0.07
    /release
    -0.07
    联网
    -0.07
    redients
    -0.06
     daycare
    -0.06
    olders
    -0.06
    spotify
    -0.06
     networks
    -0.06
    POSITIVE LOGITS
     pleasantly
    0.06
     provoke
    0.06
    …and
    0.06
    upper
    0.06
     patented
    0.06
    appear
    0.06
     neph
    0.06
     eag
    0.06
     nguyên
    0.06
     �
    0.06
    Act Density 0.020%

    No Known Activations